Metraipolis › archive › dc_4aa62cf7eed4

Autotuning GPU Thread Block Sizes for Large-Scale Stencil Applications Using the OPS DSL — arXiv:2611.00968

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00968
License (as archived)
CC0-1.0
Archived
2026-11-03T11:12:36.352Z
SHA-256 of the archived text
b183d334a06d93b166efaae5dbff9447b706e63cd7c933d031749cffcae9d1a0
Stable URL of this page
https://metraipolis.com/documento/dc_4aa62cf7eed4

How to cite

Autotuning GPU Thread Block Sizes for Large-Scale Stencil Applications Using the OPS DSL — arXiv:2611.00968 — arXiv (en), https://arxiv.org/abs/2611.00968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4aa62cf7eed4 (Metraipolis archive dc_4aa62cf7eed4, sha256 b183d334a06d93b166efaae5dbff9447b706e63cd7c933d031749cffcae9d1a0)
BibTeX
@misc{dc4aa62cf7eed4,
  title = {Autotuning GPU Thread Block Sizes for Large-Scale Stencil Applications Using the OPS DSL — arXiv:2611.00968},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00968},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4aa62cf7eed4; sha256 b183d334a06d93b166efaae5dbff9447b706e63cd7c933d031749cffcae9d1a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large-scale structured-mesh stencil applications can run for hours or days on modern HPC GPU platforms, making launch-configuration choices important. OPS enables high-level stencil codes to target multiple GPU architectures, but its GPU backends rely on a default or user-selected global block/workgroup shape, even though different kernels, problem geometries, and architectures may favor different configurations. This paper presents a transparent per-kernel block/workgroup-shape autotuning extension for OPS. The extension explores valid block/workgroup shapes during execution, records the fastest configuration for each kernel, and enables precomputed replay of the selected configurations in subsequent runs. We evaluate the approach on structured-mesh proxy and academic research applications, covering 459 unique kernels across 3 NVIDIA and 2 AMD GPUs. The evaluation reports speedup distributions, representative wall-time summaries, timing variability, and input problem shape effects. Replaying the best per-kernel launch shapes improves 923 of 995 measured application/input/GPU cases over the default OPS shape. Depending on the GPU, the median speedup ranges from 1.02x to 1.18x, with individual configurations of LAPL2D, TTI3D, and OpenSBLI-based TGV solvers exceeding 1.5x. The results also show that performance sensitivity is not limited to launch shape. At fixed cell count, changing the input problem shape changes precomputed-replay runtime by 0.8-34.6% in representative cases, while kernel-level timing variability depends on the interaction between runtime contribution, input problem shape, and GPU/backend behavior. Overall, automatic per-kernel block/workgroup-shape selection improves OPS performance across GPUs, provided shape sensitivity and timing stability are interpreted together.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2611.00968 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T11:00:07.145Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).